Xiaojin Gong

Ms. Xiaojin Gong


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2019 in IEEE Access
Verified
Journal Article
Open access
NWNingning Wang
Ningning Wang
XGXiaojin Gong
Xiaojin Gong
RGB-D (Red, Green, Blue, and Depth) salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images. Based upon an observation that most of the salient objects may stand out at least in one modality, this paper proposes an adaptive fusion scheme to fuse saliency predictions generated from two modalities. Specifically, we design a two-streamed convolutional neural network (CNN), each of which extracts features and predicts a saliency map from either RGB or depth modality. Then, a saliency fusion module learns a switch map that is used to adaptively fuse the predicted saliency maps. A loss function composed of saliency supervision, switch map supervision, and edge-preserving constraints is designed to make full supervision, and the entire network is trained in an end-to-end manner. Benefited from the adaptive fusion strategy and the edge-preserving constraint, our approach outperforms state-of-the-art methods on three publicly available datasets.

1 February 2013 in Sensors
Verified
Journal Article
Open access
PDF file
XGXiaojin Gong
Xiaojin Gong
YLYing Lin
Ying Lin
JLJilin Liu
Jilin Liu
This paper presents a novel way to address the extrinsic calibration problem for a system composed of a 3D LIDAR and a camera. The relative transformation between the two sensors is calibrated via a nonlinear least squares (NLS) problem, which is formulated in terms of the geometric constraints associated with a trihedral object. Precise initial estimates of NLS are obtained by dividing it into two sub-problems that are solved individually. With the precise initializations, the calibration parameters are further refined by iteratively optimizing the NLS problem. The algorithm is validated on both simulated and real data, as well as a 3D reconstruction application. Moreover, since the trihedral target used for calibration can be either orthogonal or not, it is very often present in structured environments, making the calibration convenient.

14 January 2020 in IEEE Access
Verified
Journal Article
Open access
QYQi Yao
Qi Yao
XGXiaojin Gong
Xiaojin Gong
Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest. However, its performance is still inferior to the fully supervised counterparts. To mitigate the performance gap, we propose a saliency guided self-attention network (SGAN) to address the WSSS problem. The introduced self-attention mechanism is able to capture rich and extensive contextual information but may mis-spread attentions to unexpected regions. In order to enable this mechanism to work effectively under weak supervision, we integrate class-agnostic saliency priors into the self-attention mechanism and utilize class-specific attention cues as an additional supervision for SGAN. Our SGAN is able to produce dense and accurate localization cues so that the segmentation performance is boosted. Moreover, by simply replacing the additional supervisions with partially labeled ground-truth, SGAN works effectively for semi-supervised semantic segmentation as well. Experiments on the PASCAL VOC 2012 and COCO datasets show that our approach outperforms all other state-of-the-art methods in both weakly and semi-supervised settings.

23 July 2018 in IEEE Access
Verified
Journal Article
Open access
XGXiaojin Gong
Xiaojin Gong
QYQi Yao
Qi Yao
MWMenglin Wang
Menglin Wang
YLYing Lin
Ying Lin
Due to the high precision and non-contact characteristics, infrared thermography has been widely used in equipment inspection to ensure the safety of electric power systems. A fundamental step toward automatic inspection and diagnosis is the detection of equipment in thermal images. Therefore, this paper presents a deep learning approach to detect equipment parts in real-time. Specifically, we propose a deep convolutional neural network that predicts the coordinates, orientation angle, and class type of each equipment part. A prior concerning orientation consistency between parts is also incorporated into our model to improve the prediction results. For evaluation, we construct a large image set containing various kinds of scenarios. Experiments on the data set show that our method is robust to noise, achieving 93.7% mean average precision when the intersection over union threshold is 0.5, and running at 20 fps on GPU. We believe that our high accurate detection results can benefit the subsequent diagnosis.

14 October 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MWMenglin Wang
Menglin Wang
JLJiachen Li
Jiachen Li
BLBaisheng Lai
Baisheng Lai
XGXiaojin Gong
Xiaojin Gong
XHXian-Sheng Hua
Xian-Sheng Hua
Recently, unsupervised person re-identification (Re-ID) has received increasing research attention due to its potential for label-free applications. A promising way to address unsupervised Re-ID is clustering-based, which generates pseudo labels by clustering and uses the pseudo labels to train a Re-ID model iteratively. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the intra-cluster variance mainly caused by the change of cameras. To address this issue, we propose to split each single cluster into multiple proxies according to camera views. The camera-aware proxies explicitly capture local structures within clusters, by which the intra-ID variance and inter-ID similarity can be better tackled. Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results. The offline association directly associates proxies according to the clustering and splitting results, while the online strategy dynamically associates proxies in terms of up-to-date features to reduce the noise caused by the delayed update of pseudo labels. The combination of two losses enables us to train a desirable Re-ID model. Extensive experiments on three person Re-ID datasets and one vehicle Re-ID dataset show that our proposed approach demonstrates competitive performance with state-of-the-art methods. Code will be available at: https://github.com/Terminator8758/O2CAP .

4 September 2014 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
WHWenqi Huang
Wenqi Huang
XGXiaojin Gong
Xiaojin Gong
MYMichael Ying Yang
Michael Ying Yang
With the advent of powerful ranging and visual sensors, nowadays, it is convenient to collect sparse 3-D point clouds and aligned high-resolution images. Benefitted from such convenience, this letter proposes a joint method to perform both depth assisted object-level image segmentation and image guided depth upsampling. To this end, we formulate these two tasks together as a bi-task labeling problem, defined in a Markov random field. An alternating direction method (ADM) is adopted for the joint inference, solving each sub-problem alternatively. More specifically, the sub-problem of image segmentation is solved by Graph Cuts, which attains discrete object labels efficiently. Depth upsampling is addressed via solving a linear system that recovers continuous depth values. By this joint scheme, robust object segmentation results and high-quality dense depth maps are achieved. The proposed method is applied to the challenging KITTI vision benchmark suite, as well as the Leuven dataset for validation. Comparative experiments show that our method outperforms stand-alone approaches.